{"total":552,"rows":[{"id":"2310.16789","title":"Detecting Pretraining Data from Large Language Models","created":"2023-10-25","cited_by_count":387,"area":null},{"id":"2103.07853","title":"Membership Inference Attacks on Machine Learning: A Survey","created":"2021-03-14","cited_by_count":321,"area":"safety"},{"id":"2408.07666","title":"Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities","created":"2024-08-14","cited_by_count":254,"area":null},{"id":"2111.09839","title":"Training Neural Networks with Fixed Sparse Masks","created":"2021-11-18","cited_by_count":214,"area":null},{"id":"2211.15583","title":"On the Effectiveness of Parameter-Efficient Fine-Tuning","created":"2022-11-28","cited_by_count":141,"area":null},{"id":"2111.10603","title":"Reasonable Effectiveness of Random Weighting: A Litmus Test for Multi-Task Learning","created":"2021-11-20","cited_by_count":101,"area":null},{"id":"2202.06526","title":"Benign Overfitting in Two-layer Convolutional Neural Networks","created":"2022-02-14","cited_by_count":91,"area":null},{"id":"2102.00931","title":"Information-Theoretic Generalization Bounds for Stochastic Gradient Descent","created":"2021-02-01","cited_by_count":84,"area":null},{"id":"2103.01516","title":"Private Stochastic Convex Optimization: Optimal Rates in $\\ell_1$ Geometry","created":"2021-03-02","cited_by_count":83,"area":null},{"id":"2103.09992","title":"Topology-Aware Segmentation Using Discrete Morse Theory","created":"2021-03-18","cited_by_count":75,"area":null},{"id":"2105.14602","title":"On the geometry of generalization and memorization in deep neural networks","created":"2021-05-30","cited_by_count":73,"area":null},{"id":"2209.14863","title":"Neural Networks Efficiently Learn Low-Dimensional Representations with SGD","created":"2022-09-29","cited_by_count":63,"area":null},{"id":"2205.13710","title":"Privacy of Noisy Stochastic Gradient Descent: More Iterations without More Privacy Loss","created":"2022-05-27","cited_by_count":61,"area":null},{"id":"2206.03996","title":"Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learning","created":"2022-06-08","cited_by_count":58,"area":null},{"id":"2303.03108","title":"Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization","created":"2023-03-03","cited_by_count":57,"area":null},{"id":"2203.00263","title":"Private Convex Optimization via Exponential Mechanism","created":"2022-03-01","cited_by_count":49,"area":null},{"id":"2401.10371","title":"Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning","created":"2024-01-18","cited_by_count":49,"area":"safety"},{"id":"2402.11867","title":"LoRA Training in the NTK Regime has No Spurious Local Minima","created":"2024-02-19","cited_by_count":48,"area":null},{"id":"2107.05585","title":"Differentially Private Stochastic Optimization: New Results in Convex and Non-Convex Settings","created":"2021-07-12","cited_by_count":45,"area":null},{"id":"2103.12024","title":"Stability and Deviation Optimal Risk Bounds with Convergence Rate $O(1/n)$","created":"2021-03-22","cited_by_count":42,"area":null},{"id":"2301.11500","title":"Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing","created":"2023-01-27","cited_by_count":42,"area":null},{"id":"2111.12229","title":"Subspace Adversarial Training","created":"2021-11-24","cited_by_count":41,"area":null},{"id":"2305.08048","title":"Towards Understanding the Generalization of Graph Neural Networks","created":"2023-05-14","cited_by_count":41,"area":null},{"id":"2302.04451","title":"Generalization in Graph Neural Networks: Improved PAC-Bayesian Bounds on Graph Diffusion","created":"2023-02-09","cited_by_count":40,"area":null},{"id":"2201.08025","title":"Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape","created":"2022-01-20","cited_by_count":39,"area":null},{"id":"2102.01117","title":"SGD Generalizes Better Than GD (And Regularization Doesn't Help)","created":"2021-02-01","cited_by_count":38,"area":null},{"id":"2206.05187","title":"On Convergence of FedProx: Local Dissimilarity Invariant Bounds, Non-smoothness and Beyond","created":"2022-06-10","cited_by_count":38,"area":null},{"id":"2206.12680","title":"Topology-aware Generalization of Decentralized SGD","created":"2022-06-25","cited_by_count":38,"area":null},{"id":"2110.02424","title":"Spectral Bias in Practice: The Role of Function Frequency in Generalization","created":"2021-10-06","cited_by_count":37,"area":null},{"id":"2302.09483","title":"Why Is Public Pretraining Necessary for Private Model Training?","created":"2023-02-19","cited_by_count":37,"area":null},{"id":"2102.03832","title":"Generalization of Model-Agnostic Meta-Learning Algorithms: Recurring and Unseen Tasks","created":"2021-02-07","cited_by_count":36,"area":null},{"id":"2105.03793","title":"Stability and Generalization of Stochastic Gradient Methods for Minimax Problems","created":"2021-05-08","cited_by_count":36,"area":null},{"id":"2106.00490","title":"Dynamic Scheduling for Over-the-Air Federated Edge Learning with Energy Constraints","created":"2021-05-31","cited_by_count":36,"area":null},{"id":"2107.10171","title":"Leave-one-out Unfairness","created":"2021-07-21","cited_by_count":36,"area":null},{"id":"2111.12292","title":"Improved Fine-Tuning by Better Leveraging Pre-Training Data","created":"2021-11-24","cited_by_count":36,"area":null},{"id":"2305.20057","title":"Three-Way Trade-Off in Multi-Objective Learning: Optimization, Generalization and Conflict-Avoidance","created":"2023-05-31","cited_by_count":36,"area":null},{"id":"2303.04145","title":"Benign Overfitting for Two-layer ReLU Convolutional Neural Networks","created":"2023-03-07","cited_by_count":34,"area":null},{"id":"2102.05274","title":"Stability of SGD: Tightness Analysis and Improved Bounds","created":"2021-02-10","cited_by_count":33,"area":null},{"id":"2110.08611","title":"Deep Active Learning by Leveraging Training Dynamics","created":"2021-10-16","cited_by_count":32,"area":null},{"id":"2106.04188","title":"Stability and Generalization of Bilevel Programming in Hyperparameter Optimization","created":"2021-06-08","cited_by_count":31,"area":null},{"id":"2110.03128","title":"On the Generalization of Models Trained with SGD: Information-Theoretic Bounds and Implications","created":"2021-10-07","cited_by_count":31,"area":null},{"id":"2102.06589","title":"Generalization Bounds for Meta-Learning via PAC-Bayes and Uniform Stability","created":"2021-02-12","cited_by_count":30,"area":null},{"id":"2106.09779","title":"Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex Losses","created":"2021-06-17","cited_by_count":30,"area":null},{"id":"2108.05574","title":"Implicit Sparse Regularization: The Impact of Depth and Early Stopping","created":"2021-08-12","cited_by_count":30,"area":null},{"id":"2210.00960","title":"Stability Analysis and Generalization Bounds of Adversarial Training","created":"2022-10-03","cited_by_count":30,"area":null},{"id":"2107.12580","title":"Pointer Value Retrieval: A new benchmark for understanding the limits of neural network generalization","created":"2021-07-27","cited_by_count":29,"area":null},{"id":"2202.13441","title":"Stability vs Implicit Bias of Gradient Methods on Separable Data and Beyond","created":"2022-02-27","cited_by_count":29,"area":null},{"id":"2103.17182","title":"Positive-Negative Momentum: Manipulating Stochastic Gradient Noise to Improve Generalization","created":"2021-03-31","cited_by_count":28,"area":null},{"id":"2109.00817","title":"NASI: Label- and Data-agnostic Neural Architecture Search at Initialization","created":"2021-09-02","cited_by_count":28,"area":null},{"id":"2108.00781","title":"Generalization Bounds using Lower Tail Exponents in Stochastic Optimizers","created":"2021-08-02","cited_by_count":27,"area":null},{"id":"2111.12876","title":"Time-independent Generalization Bounds for SGLD in Non-convex Settings","created":"2021-11-25","cited_by_count":27,"area":null},{"id":"2306.03824","title":"Understanding Generalization of Federated Learning via Stability: Heterogeneity Matters","created":"2023-06-06","cited_by_count":27,"area":null},{"id":"2307.11108","title":"Flatness-Aware Minimization for Domain Generalization","created":"2023-07-20","cited_by_count":27,"area":null},{"id":"2107.12723","title":"Stability & Generalisation of Gradient Descent for Shallow Neural Networks without the Neural Tangent Kernel","created":"2021-07-27","cited_by_count":26,"area":null},{"id":"2206.08684","title":"Sparse Double Descent: Where Network Pruning Aggravates Overfitting","created":"2022-06-17","cited_by_count":26,"area":null},{"id":"2304.09595","title":"AdapterGNN: Parameter-Efficient Fine-Tuning Improves Generalization in GNNs","created":"2023-04-19","cited_by_count":26,"area":null},{"id":"2305.18424","title":"Repeated Random Sampling for Minimizing the Time-to-Accuracy of Learning","created":"2023-05-28","cited_by_count":26,"area":null},{"id":"2405.13629","title":"Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow","created":"2024-05-22","cited_by_count":26,"area":"deeprl"},{"id":"2405.14369","title":"RoPINN: Region Optimized Physics-Informed Neural Networks","created":"2024-05-23","cited_by_count":26,"area":null},{"id":"2203.10036","title":"On the Generalization Mystery in Deep Learning","created":"2022-03-18","cited_by_count":25,"area":null},{"id":"2206.07082","title":"Stability and Generalization of Stochastic Optimization with Nonconvex and Nonsmooth Problems","created":"2022-06-14","cited_by_count":25,"area":null},{"id":"2305.17476","title":"Toward Understanding Generative Data Augmentation","created":"2023-05-27","cited_by_count":25,"area":null},{"id":"2507.20016","title":"FedSWA: Improving Generalization in Federated Learning with Highly Heterogeneous Data via Momentum-Based Stochastic Controlled Weight Averaging","created":"2025-07-26","cited_by_count":25,"area":null},{"id":"2201.09046","title":"Differentially Private SGDA for Minimax Problems","created":"2022-01-22","cited_by_count":23,"area":null},{"id":"2206.07252","title":"Implicit Regularization or Implicit Conditioning? Exact Risk Trajectories of SGD in High Dimensions","created":"2022-06-15","cited_by_count":23,"area":null},{"id":"2101.08925","title":"Differentially Private SGD with Non-Smooth Losses","created":"2021-01-22","cited_by_count":22,"area":null},{"id":"2111.07167","title":"The Three Stages of Learning Dynamics in High-Dimensional Kernel Methods","created":"2021-11-13","cited_by_count":22,"area":null},{"id":"2206.00363","title":"Bring Your Own Algorithm for Optimal Differentially Private Stochastic Minimax Optimization","created":"2022-06-01","cited_by_count":22,"area":null},{"id":"2208.04508","title":"Training Overparametrized Neural Networks in Sublinear Time","created":"2022-08-09","cited_by_count":22,"area":null},{"id":"2103.15352","title":"Private Non-smooth Empirical Risk Minimization and Stochastic Convex Optimization in Subquadratic Steps","created":"2021-03-29","cited_by_count":21,"area":null},{"id":"2209.09298","title":"Stability and Generalization Analysis of Gradient Methods for Shallow Neural Networks","created":"2022-09-19","cited_by_count":21,"area":null},{"id":"2210.08285","title":"FedCross: Towards Accurate Federated Learning via Multi-Model Cross-Aggregation","created":"2022-10-15","cited_by_count":21,"area":null},{"id":"2302.09235","title":"Generalization and Stability of Interpolating Neural Networks with Minimal Width","created":"2023-02-18","cited_by_count":21,"area":null},{"id":"2306.05706","title":"Understanding How Consistency Works in Federated Learning via Stage-wise Relaxed Initialization","created":"2023-06-09","cited_by_count":21,"area":null},{"id":"2105.00303","title":"RATT: Leveraging Unlabeled Data to Guarantee Generalization","created":"2021-05-01","cited_by_count":20,"area":null},{"id":"2109.00267","title":"The Impact of Reinitialization on Generalization in Convolutional Neural Networks","created":"2021-09-01","cited_by_count":20,"area":null},{"id":"2110.04514","title":"Towards Open-World Feature Extrapolation: An Inductive Graph Learning Approach","created":"2021-10-09","cited_by_count":20,"area":null},{"id":"2111.12050","title":"Simple Stochastic and Online Gradient Descent Algorithms for Pairwise Learning","created":"2021-11-23","cited_by_count":20,"area":null},{"id":"2205.13532","title":"Selective Prediction via Training Dynamics","created":"2022-05-26","cited_by_count":20,"area":null},{"id":"2206.03317","title":"Subject Membership Inference Attacks in Federated Learning","created":"2022-06-07","cited_by_count":20,"area":"safety"},{"id":"2306.00788","title":"Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression","created":"2023-06-01","cited_by_count":20,"area":null},{"id":"2104.09342","title":"Random Reshuffling with Variance Reduction: New Analysis and Better Rates","created":"2021-04-19","cited_by_count":19,"area":null},{"id":"2112.10224","title":"Stable Conformal Prediction Sets","created":"2021-12-19","cited_by_count":19,"area":null},{"id":"2202.13361","title":"Benign Underfitting of Stochastic Gradient Descent","created":"2022-02-27","cited_by_count":19,"area":null},{"id":"2204.12446","title":"Beyond Lipschitz: Sharp Generalization and Excess Risk Bounds for Full-Batch GD","created":"2022-04-26","cited_by_count":19,"area":null},{"id":"2212.13556","title":"Limitations of Information-Theoretic Generalization Bounds for Gradient Descent Methods in Stochastic Convex Optimization","created":"2022-12-27","cited_by_count":19,"area":null},{"id":"2301.12600","title":"Bagging Provides Assumption-free Stability","created":"2023-01-30","cited_by_count":19,"area":null},{"id":"2309.13658","title":"Fantastic Generalization Measures are Nowhere to be Found","created":"2023-09-24","cited_by_count":19,"area":null},{"id":"2211.11656","title":"SIFU: Sequential Informed Federated Unlearning for Efficient and Provable Client Unlearning in Federated Optimization","created":"2022-11-21","cited_by_count":18,"area":"safety"},{"id":"2102.10234","title":"Generalization bounds for graph convolutional neural networks via Rademacher complexity","created":"2021-02-20","cited_by_count":17,"area":null},{"id":"2104.02988","title":"Optimal Algorithms for Differentially Private Stochastic Monotone Variational Inequalities and Saddle-Point Problems","created":"2021-04-07","cited_by_count":17,"area":null},{"id":"2105.11558","title":"Near-optimal Offline and Streaming Algorithms for Learning Non-Linear Dynamical Systems","created":"2021-05-24","cited_by_count":17,"area":null},{"id":"2106.09805","title":"Shuffle Private Stochastic Convex Optimization","created":"2021-06-17","cited_by_count":17,"area":null},{"id":"2106.10414","title":"Deep Learning for Functional Data Analysis with Adaptive Basis Layers","created":"2021-06-19","cited_by_count":17,"area":null},{"id":"2202.06915","title":"Stochastic linear optimization never overfits with quadratically-bounded losses on general data","created":"2022-02-14","cited_by_count":17,"area":null},{"id":"2205.03014","title":"Differentially Private Generalized Linear Models Revisited","created":"2022-05-06","cited_by_count":17,"area":null},{"id":"2101.04968","title":"Learning with Gradient Descent and Weakly Convex Losses","created":"2021-01-13","cited_by_count":16,"area":null},{"id":"2102.00127","title":"On Data Efficiency of Meta-learning","created":"2021-01-30","cited_by_count":16,"area":null},{"id":"2102.02167","title":"Algorithmic Instabilities of Accelerated Gradient Descent","created":"2021-02-03","cited_by_count":16,"area":null},{"id":"2111.08911","title":"Fast Rates for Nonparametric Online Learning: From Realizability to Learning in Games","created":"2021-11-17","cited_by_count":16,"area":null}],"next_cursor":"100"}